FunASR
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Install
Dockerstdio
docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2 Client config (Claude Desktop, Cursor, Windsurf and most MCP clients)
{
"mcpServers": {
"io-github-modelscope-funasr-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
} Source: official MCP Registry record · registry name io.github.modelscope/funasr-mcp · published 2026-07-26 · updated 2026-07-26. Not an endorsement; review the code before connecting it to anything sensitive.